Normalized claim
Accuracy: 100%
The intelligent ticketing system achieved 100 percent accuracy on complex queries in follow-up responses.
Kingdee International Software Group deployed generative AI features to improve ERP usability and let users retrieve complex data and complete multi-step tasks through natural language. The company built an intelligent ticketing system and an intelligent metrics analysis tool on Amazon Bedrock, integrating agents with Kingdee APIs, knowledge bases, databases, Lambda, API Gateway, and OpenSearch. The system also uses Text2SQL through Bedrock Agents and provides a 24/7 virtual assistant for managers and end users.
Reported outcomes
100%
accuracyQuality & accuracy
Strategic outcomes
Normalized claim
Accuracy: 100%
The intelligent ticketing system achieved 100 percent accuracy on complex queries in follow-up responses.
Normalized claim
Accuracy: 90%
The metrics tool achieved over 90 percent first-round response accuracy for straightforward queries.
Normalized claim
Accuracy: 70-80%
Complex queries reached 70 to 80 percent accuracy initially before achieving 100 percent accuracy on follow-up responses.
Kingdee International Software Group deployed generative AI features to improve ERP usability and let users retrieve complex data and complete multi-step tasks through natural language
Primary read
Showing 3 of 4
Kingdee built intelligent ticketing and metrics analysis solutions on Amazon Bedrock. The implementation uses Amazon Bedrock Agents integrated with Kingdee APIs, databases, AWS Lambda, Amazon API Gateway, and Amazon OpenSearch Service, plus a Text2SQL workflow for natural-language access to ERP data.
AI-generated summary. Verify important details with the linked sources before relying on this case.
Was this useful?
Community
Loading comments...